1

EarlyBERT: Efficient BERT Training via Early-bird Lottery Tickets

Heavily overparameterized language models such as BERT, XLNet and T5 have achieved impressive success in many NLP tasks. However, their high model complexity requires enormous computation resources and extremely long training time for both …

A Design Space Study for LISTA and Beyond

In recent years, great success has been witnessed in building problem-specific deep networks from unrolling iterative algorithms, for solving inverse problems and beyond. Unrolling is believed to incorporate the model-based prior with the learning …

Learning A Minimax Optimizer: A Pilot Study

Solving continuous minimax optimization is of extensive practical interest, yet notoriously unstable and difficult. This paper introduces the learning to optimize (L2O) methodology to the minimax problems for the first time, and addresses its …

SmartDeal: Re-Modeling Deep Network Weights for Efficient Inference and Training

The record-breaking performance of deep neural networks (DNNs) comes with heavy parameterization, leading to external dynamic random-access memory (DRAM) for storage. The prohibitive energy of DRAM accesses makes it non-trivial to deploy DNN on …

MATE: Plugging in Model Awareness to Task Embedding for Meta Learning

Meta-learning improves generalization of machine learning models when faced with previously unseen tasks by leveraging experiences from different, yet related prior tasks. To allow for better generalization, we propose a novel task representation …

ShiftAddNet: A Hardware-Inspired Deep Network

Multiplication (e.g., convolution) is arguably a cornerstone of modern deep neural networks (DNNs). However, intensive multiplications cause expensive resource costs that challenge DNN deployment on resource-constrained edge devices, driving several …

Uncertainty Quantification for Deep Context-Aware Mobile Activity Recognition and Unknown Context Discovery

Activity recognition in wearable computing faces two key challenges: i) activity characteristics may be context-dependent and change under different contexts or situations; ii) unknown contexts and activities may occur from time to time, requiring …

SmartExchange: Trading Higher-cost Memory Storage/Access for Lower-cost Computation

We present SmartExchange, a hardware-algorithm co-design framework to trade higher cost memory storage/access for lower cost computation, for energy-efficient inference of deep neural networks (DNNs). We have developed a novel algorithm to enforce a …

Drawing Early-Bird Tickets: Toward More Efficient Training of Deep Networks

(Frankle & Carbin, 2019) shows that there exist winning tickets (small but critical subnetworks) for dense, randomly initialized networks, that can be trained alone to achieve comparable accuracies to the latter in a similar number of iterations. …

E2-Train: Energy-Efficient Deep Network Training with Data-, Model-, and Algorithm-Level Saving

Convolutional neural networks (CNNs) have been increasingly deployed to Internet of Things (IoT) devices. Hence, many efforts have been made towards efficient CNN inference in resource-constrained platforms. This paper attempts to explore an …